Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911633204314112 |
|---|---|
| author | Ramezani, Mahya Voos, Holger |
| author_facet | Ramezani, Mahya Voos, Holger |
| contents | This paper presents a hierarchical decision-making framework for unmanned aerial vehicle (UAV) missions motivated by search-and-rescue (SAR) scenarios under limited simulation training. The framework combines a fixed rule-based high-level advisor with an online goal-conditioned low-level reinforcement learning (RL) controller. To stress-test early adaptation, we also consider a strict no-pretraining deployment regime. The high-level advisor is defined offline from a structured task specification and compiled into deterministic rules. It provides interpretable mission- and safety-aware guidance through recommended actions, avoided actions, and regime-dependent arbitration weights. The low-level controller learns online from task-defined dense rewards and reuses experience through a mode-aware prioritized replay mechanism augmented with rule-derived metadata. We evaluate the framework on two tasks: battery-aware multi-goal delivery and moving-target delivery in obstacle-rich environments. Across both tasks, the proposed method improves early safety and sample efficiency primarily by reducing collision terminations, while preserving the ability to adapt online to scenario-specific dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26833 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training Ramezani, Mahya Voos, Holger Robotics Artificial Intelligence Machine Learning This paper presents a hierarchical decision-making framework for unmanned aerial vehicle (UAV) missions motivated by search-and-rescue (SAR) scenarios under limited simulation training. The framework combines a fixed rule-based high-level advisor with an online goal-conditioned low-level reinforcement learning (RL) controller. To stress-test early adaptation, we also consider a strict no-pretraining deployment regime. The high-level advisor is defined offline from a structured task specification and compiled into deterministic rules. It provides interpretable mission- and safety-aware guidance through recommended actions, avoided actions, and regime-dependent arbitration weights. The low-level controller learns online from task-defined dense rewards and reuses experience through a mode-aware prioritized replay mechanism augmented with rule-derived metadata. We evaluate the framework on two tasks: battery-aware multi-goal delivery and moving-target delivery in obstacle-rich environments. Across both tasks, the proposed method improves early safety and sample efficiency primarily by reducing collision terminations, while preserving the ability to adapt online to scenario-specific dynamics. |
| title | Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.26833 |